{
  "best_metric": 2.689387321472168,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.03468208092485549,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0011560693641618498,
      "eval_loss": 5.355404376983643,
      "eval_runtime": 10.3348,
      "eval_samples_per_second": 35.318,
      "eval_steps_per_second": 17.707,
      "step": 1
    },
    {
      "epoch": 0.003468208092485549,
      "grad_norm": 11.751943588256836,
      "learning_rate": 0.00012,
      "loss": 4.8871,
      "step": 3
    },
    {
      "epoch": 0.005780346820809248,
      "eval_loss": 4.043927192687988,
      "eval_runtime": 9.8354,
      "eval_samples_per_second": 37.111,
      "eval_steps_per_second": 18.606,
      "step": 5
    },
    {
      "epoch": 0.006936416184971098,
      "grad_norm": 8.5070161819458,
      "learning_rate": 0.0001992114701314478,
      "loss": 4.4911,
      "step": 6
    },
    {
      "epoch": 0.010404624277456647,
      "grad_norm": 11.9057035446167,
      "learning_rate": 0.00018763066800438636,
      "loss": 3.0416,
      "step": 9
    },
    {
      "epoch": 0.011560693641618497,
      "eval_loss": 2.960925817489624,
      "eval_runtime": 9.7286,
      "eval_samples_per_second": 37.518,
      "eval_steps_per_second": 18.811,
      "step": 10
    },
    {
      "epoch": 0.013872832369942197,
      "grad_norm": 7.719348907470703,
      "learning_rate": 0.000163742398974869,
      "loss": 2.4484,
      "step": 12
    },
    {
      "epoch": 0.017341040462427744,
      "grad_norm": 9.678977012634277,
      "learning_rate": 0.00013090169943749476,
      "loss": 2.8573,
      "step": 15
    },
    {
      "epoch": 0.017341040462427744,
      "eval_loss": 2.837536096572876,
      "eval_runtime": 10.103,
      "eval_samples_per_second": 36.128,
      "eval_steps_per_second": 18.113,
      "step": 15
    },
    {
      "epoch": 0.020809248554913295,
      "grad_norm": 5.845253944396973,
      "learning_rate": 9.372094804706867e-05,
      "loss": 2.6995,
      "step": 18
    },
    {
      "epoch": 0.023121387283236993,
      "eval_loss": 2.750244379043579,
      "eval_runtime": 9.6981,
      "eval_samples_per_second": 37.636,
      "eval_steps_per_second": 18.87,
      "step": 20
    },
    {
      "epoch": 0.024277456647398842,
      "grad_norm": 12.756491661071777,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 2.7991,
      "step": 21
    },
    {
      "epoch": 0.027745664739884393,
      "grad_norm": 8.277565956115723,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 2.1547,
      "step": 24
    },
    {
      "epoch": 0.028901734104046242,
      "eval_loss": 2.698179244995117,
      "eval_runtime": 9.9751,
      "eval_samples_per_second": 36.591,
      "eval_steps_per_second": 18.346,
      "step": 25
    },
    {
      "epoch": 0.03121387283236994,
      "grad_norm": 7.9303297996521,
      "learning_rate": 7.022351411174866e-06,
      "loss": 2.4543,
      "step": 27
    },
    {
      "epoch": 0.03468208092485549,
      "grad_norm": 8.284680366516113,
      "learning_rate": 0.0,
      "loss": 2.401,
      "step": 30
    },
    {
      "epoch": 0.03468208092485549,
      "eval_loss": 2.689387321472168,
      "eval_runtime": 9.9846,
      "eval_samples_per_second": 36.556,
      "eval_steps_per_second": 18.328,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 540715725619200.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}